CN102486751A - Method for realizing virtual big page through small page NANDFLASH on micro memory system - Google Patents
Method for realizing virtual big page through small page NANDFLASH on micro memory system Download PDFInfo
- Publication number
- CN102486751A CN102486751A CN2010105684856A CN201010568485A CN102486751A CN 102486751 A CN102486751 A CN 102486751A CN 2010105684856 A CN2010105684856 A CN 2010105684856A CN 201010568485 A CN201010568485 A CN 201010568485A CN 102486751 A CN102486751 A CN 102486751A
- Authority
- CN
- China
- Prior art keywords
- page
- leaf
- little
- nandflash
- big
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000008569 process Effects 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000033772 system development Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008521 reorganization Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Landscapes
- Memory System (AREA)
Abstract
The invention discloses a method for realizing a virtual big page through a small page NANDFLASH on a micro memory system. The method comprises the following steps: separating the NANDFLASH driving of big pages from the NANDFLASH driving of small pages; virtualizing a plurality of physical small pages into a logic big page; and virtualizing a plurality of physical small blocks into a logic big block. According to the method, a non-mainstream small page Nandflash can be used as a mainstream big page Nandflash, the complexity in calling an upper layer is greatly reduced, and meanwhile, an internal memory space occupied by the small page Nandflash management is greatly reduced for the micro memory system with ultra-small internal memory.
Description
Technical field
The present invention relates to a kind of disposal route of embedded system storer, relate in particular to a kind of method that on little memory system, realizes the virtual big page or leaf of little page or leaf NANDFLAH.
Background technology
In the current all kinds of embedded system development design, memory module is indispensable vitals.Flash storer wherein has series of advantages such as volume is little, capacity is big, cost is low, the power down data are not lost as a kind of safe, memory bank fast.Progressively replace other semiconductor memory component at present, become the main carrier of data and program in the embedded system.
The Nandflash technical development is swift and violent, and the Nandflash product line of different vendor is all constantly being weeded out the old and bring forth the new.With regard to regard to a series of NANDFLASH upgrading, in M generation, A generation, B generation, arranged ... Branch, like K9G4G08X0M, K9G4G08X0A and the K9G4G08X0B of Samsung; With regard to the nanometer production technology, 70nm, 52nm, 34nm, 32nm are arranged ... Branch, the production technology of the more little expression of nm number manufacturer is more accurate.With regard to the variation of block, the branch of 16KB, 128KB, 256KB, 512KB, 1MB, 2MB is arranged; With regard to the variation of page, the branch of 512B, 2KB, 4KB, 8KB is arranged.Block and page are big more, have generally also represented production technology more advanced.
In numerous and complicated nandflash product line, the page that occurs the earliest is that 512B, block are that the nandflash of 16KB is called as small page nandflash (being little page or leaf nandflash), the market of having faded out gradually.But small stock is still arranged on the market, or the little page or leaf of this type nandflash is also arranged among the old Nandflash that disassembles of some old electronic products.And except that little page or leaf nandflash, other nandflash are referred to as big page or leaf nandflash no matter it is the nandflash of SLC (single level cell, single stage unit) or MLC (multi level cell, multi-level unit) type.
For these internal memory software systems slightly, need under limited memory source, support various nandflash, wherein just comprise little page or leaf nandflash.But still do not have at present method preferably and realize the special processing on little internal memory software and hardware scheme little page or leaf nandflash carried out.In various general schemes, all be to use the little page or leaf nandflash that this type of nandflash is used as standard.
Prior art is used little page or leaf nandflash in a conventional manner, but this mode has following shortcoming: first for little memory system: size page or leaf nand drives and integrates, and committed memory is more; Second: the page or leaf of little page or leaf nandflash has only 512B, and inconvenient little memory system carries out skip operation and read resource operation of internal memory; The 3rd: the piece of little page or leaf nandflash has only 16KB, and in the therefore equal capacity, the nandflash of little page or leaf is more much more than the piece number of the nandflash of big page or leaf, and this brings bigger Memory Load for the piece mapping table of little memory system.
Summary of the invention
The object of the present invention is to provide a kind of method that on little memory system, realizes the virtual big page or leaf of little page or leaf NANDFLAH, the big page or leaf Nandflash that this method can be used as non-mainstream little page or leaf Nandflash main flow uses, and reduces the complexity that call on the upper strata greatly; Simultaneously, to the very nervous little memory system of internal memory, significantly reduce the memory headroom that little page of Nandflash administrative institute taken.
The object of the invention can be realized through following technical measures:
A kind of method that on little memory system, realizes the virtual big page or leaf of little page or leaf NANDFLAH at first, is driven apart big page or leaf NANDFLASH driving in the system and little page or leaf NANDFLASH; Again with the little page or leaf of physics in the system virtually become the big page or leaf of logic, with the virtual logic bulk that becomes of physics fritter.
Large and small page or leaf NANDFLASH in said little memory system drives through grand and separates.
To comprise the size of 32 little pages or leaves of physics, the little page or leaf of each physics be 512B to each physics fritter in the said little page or leaf NANDFLASH system.
Comprise 8 little pages or leaves of physics in the big page or leaf of said each virtual logic.
Comprise 16 physics fritters in said each virtual logic bulk.
The process of the big page or leaf of logic of read-write among the said little page or leaf NANDFLAH is decomposed into the little page or leaf of the some physics of read-write.
The process of wiping a logic bulk among the said little page or leaf NANDFLAH is decomposed into wipes some physics fritters.
The inventive method has following beneficial effect: at first, this method is used the big page or leaf Nandflash that non-mainstream little page or leaf Nandflash is used as main flow, reduces the complexity that call on the upper strata greatly, saves the shared resource of system call; Second: to the very nervous little memory system of internal memory, significantly reduce the memory headroom that little page of Nandflash administrative institute taken, and transparent to upper layer application; The 3rd, the inventive method can be applicable to a whole set of system development platform to products such as low and middle-end MP3, MP4, recording pen, talking pen and point reader of multimedia application process chip.
Description of drawings
Fig. 1 is with big page of composition structural representation that is divided into the little page or leaf of a plurality of physics of a logic in the inventive method;
Fig. 2 is the read-write logical schematic during the big page or leaf of logic of read-write in the inventive method;
Fig. 3 is the composition structural representation that in the inventive method a logic bulk is divided into a plurality of physics fritters;
Fig. 4 is the logical schematic of wiping when wiping a logic bulk in the inventive method;
Fig. 5 is the composition structural representation of a logic bulk in the inventive method.
Embodiment
Fig. 1 to Fig. 5 shows the structural representation of the reorganization of adopting in a kind of method that on little memory system, realizes the virtual big page or leaf of little page or leaf NANDFLAH of the present invention will the original little page or leaf NANDFLASH virtual internal storage structure that becomes a big page NANDFLASH; To comprise the size of 32 little pages or leaves of physics, the little page or leaf of each physics be 512B to each physics fritter among the little page or leaf NANDFLASH that the present invention adopts, and its particular content that invents big page or leaf NANDFLASH is comprised the following aspects:
(1), the big page or leaf nandflash driving in the system, little page or leaf nandflash are driven apart:
Because little memory system internal memory is nervous, therefore, the driving of big page or leaf nandflash and the driving of little page or leaf nandflash are separated through grand fully, what separate simultaneously also has the special little page or leaf special processing that nandflash did that is described below;
(2), with the little page or leaf of a plurality of physics in the system virtual be a big page or leaf of logic:
The employed size of skipping of little memory system is 4KB, will go exchange from the same space on the nandflash for a such page.In order to avoid the dependence of Memory Exchange administration module to the physical hardware differentiation, the page or leaf size that can let the Memory Exchange administration module can treat hardware of memory device pellucidly is 4KB.For the nandflash of little page or leaf, the page or leaf size is 512 B like this, can replace the logical page (LPAGE) size of a 4KB in logic with 8 pages or leaves physically.It is formed structure and can represent with Fig. 1, with 8 virtual big page of logics that become of the little page or leaf of physics;
When reading and writing the nandflash of little page or leaf for the Memory Exchange module like this, can obtain the 4KB data of an expectation for read-write interface at the little page or leaf of continuous 8 physics of read-write of Drive Layer.Like Fig. 2 is the read-write logic of Drive Layer; Pseudo-big page or leaf among the figure promptly is the big page or leaf of logic, and true little page or leaf is exactly the little page or leaf of physics;
(3), become a logic bulk with a plurality of physics fritters in the system are virtual:
Because all Nandflash can be divided into piece composition one by one, its base unit of wiping is a unit with the piece exactly, promptly is the logic bulk like pseudo-bulk among Fig. 4, and true fritter is exactly the physics fritter.
Possibly there is the bad piece that can not read and write data in these pieces; During for a file or the one piece of data district of read-write on the nandflash; Need know which piece is these data be kept at respectively in, so just have a piece mapping table of corresponding this file or this segment data.For little page or leaf Nandflash, an one of which physics block sizes is 16KB, the data field that is 10M for a size like this, and a piece is with 2 byte representations, and the shared space of its mapping table is:
2?×（10?×1024?×1024）?/?（16?×?1024）?=?1280?Bytes
The little relatively internal memory of occupation space is just bigger like this, also the read-write of nandflash Drive Layer also need offer other module, such as file system.For little memory system, in the management of file system to the need sum block of internal memory certain restriction and requirement are arranged also.If but we are mapped to a bulk in logic with a plurality of fritters physically (block), just can address this is that.Nandflash to some popular on present market 4KB page; The number of pages amount that piece comprised is 64 page; Be 256KB; For the little page or leaf NANDFLASH in the native system is invented passable so big page or leaf NANDFALSH, then simulate the bulk (as shown in Figure 3) of the nandflash of such 4 common KB/page, 64 page/block with 16 physics fritters among the little page or leaf NNADFLASH.Bulk after virtual is called the logic bulk, and what 16 physics fritters were corresponding is exactly 16*32 the little page or leaf of physics, and just 2*32=64 logic is big page, composition structure promptly as shown in Figure 5.
So, the big page or leaf of each logic comprises 8 little pages or leaves of physics, and each logic bulk comprises 64 big pages or leaves of logic, and whole little page or leaf NANDFLASH is reassembled as the big page or leaf NANDFLASH that comprises some logic bulks, and is as shown in Figure 5.
An application case of the inventive method is following:
A whole set of system development platform based on certain multimedia application process chip to products such as low and middle-end MP3, MP4, recording pen, talking pen and point reader.This platform adopts the virtual memory technology to embedded system, and is transparent fully to the upper strata developer need not can to fictionalize the memory headroom of 2MB or 4MB under the situation of external SDRAM, flexibly, conveniently, is easy to secondary development.This platform also possesses the strong multimedia decoding capability, supports the audio decoder function of multiple forms such as mp3/wma/wav/amr/flac/ape/ogg, and the smooth decoding capability of QVGA video.
Since native system hardware core---the multimedia application process chip only is no more than the physics sram memory of 256KB, and the virtual memory of 2MB or 4MB can be provided to the upper strata developer.Owing to used the mechanism of skipping of this method; The internal memory (code or data) that promptly will visit when the upper strata is not in physical memory; Give up to fall former data to a page of physical memory (a page size definition is 4KB), and reload the new data of a page from nandflash.
Embodiment of the present invention is not limited thereto; Under the above-mentioned basic fundamental thought of the present invention prerequisite;, all drop within the rights protection scope of the present invention modification, replacement or the change of other various ways that content of the present invention is made according to the ordinary skill knowledge of this area and customary means.
Claims (7)
1. a method that on little memory system, realizes the virtual big page or leaf of little page or leaf NANDFLAH is characterized in that: at first, big page or leaf NANDFLASH driving in the system and little page or leaf NANDFLASH are driven apart; Again with the little page or leaf of physics in the system virtually become the big page or leaf of logic, with the virtual logic bulk that becomes of physics fritter.
2. the method that on little memory system, realizes the little page of virtual big page or leaf of NANDFLAH according to claim 1 is characterized in that: the large and small page or leaf NANDFLASH in said little memory system drives through grand and separates.
3. the method that on little memory system, realizes the virtual big page or leaf of little page or leaf NANDFLAH according to claim 1 is characterized in that: to comprise the size of 32 little pages or leaves of physics, the little page or leaf of each physics be 512B to each physics fritter in the said little page or leaf NANDFLASH system.
4. the method that on little memory system, realizes the virtual big page or leaf of little page or leaf NANDFLAH according to claim 1 is characterized in that: comprise 8 little pages or leaves of physics in the big page or leaf of said each virtual logic.
5. the method that on little memory system, realizes the virtual big page or leaf of little page or leaf NANDFLAH according to claim 1 is characterized in that: comprise 16 physics fritters in said each virtual logic bulk.
6. according to claim 1 or the 4 described methods that on little memory system, realize the virtual big page or leaf of little page or leaf NANDFLAH, it is characterized in that: the process of the big page or leaf of logic of read-write among the said little page or leaf NANDFLAH is decomposed into the little page or leaf of the some physics of read-write.
7. according to claim 1 or the 5 described methods that on little memory system, realize the virtual big page or leaf of little page or leaf NANDFLAH, it is characterized in that: the process of wiping a logic bulk among the said little page or leaf NANDFLAH is decomposed into wipes some physics fritters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105684856A CN102486751A (en) | 2010-12-01 | 2010-12-01 | Method for realizing virtual big page through small page NANDFLASH on micro memory system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105684856A CN102486751A (en) | 2010-12-01 | 2010-12-01 | Method for realizing virtual big page through small page NANDFLASH on micro memory system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102486751A true CN102486751A (en) | 2012-06-06 |
Family
ID=46152248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010105684856A Pending CN102486751A (en) | 2010-12-01 | 2010-12-01 | Method for realizing virtual big page through small page NANDFLASH on micro memory system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102486751A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838608A (en) * | 2014-03-05 | 2014-06-04 | 深圳市中兴物联科技有限公司 | Method and device for page self-adaption of NAND Flash |
| CN107392200A (en) * | 2017-08-23 | 2017-11-24 | 深圳市乐智教育科技有限公司 | It is a kind of to put the method read and talking pen |
| CN108717395A (en) * | 2018-05-18 | 2018-10-30 | 记忆科技(深圳)有限公司 | A kind of method and device reducing dynamic address mapping information committed memory |
| WO2019127135A1 (en) * | 2017-12-27 | 2019-07-04 | 华为技术有限公司 | File page table management technique |
| CN112162938A (en) * | 2015-08-10 | 2021-01-01 | 北京忆恒创源科技有限公司 | Large page memory allocation method and computer thereof |
| CN112394884A (en) * | 2020-11-18 | 2021-02-23 | 珠海全志科技股份有限公司 | Method for reducing UBI subsystem management overhead, UBI subsystem and medium |
| CN113296685A (en) * | 2020-05-29 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Data processing method and device and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020044486A1 (en) * | 2000-10-16 | 2002-04-18 | Cheng-Sheng Chan | IC card with different page sizes to increase endurance |
| CN1682200A (en) * | 2002-09-13 | 2005-10-12 | 皇家飞利浦电子股份有限公司 | Translation lookaside buffer with partial tag hashed according to page size indicator |
| US20060236063A1 (en) * | 2005-03-30 | 2006-10-19 | Neteffect, Inc. | RDMA enabled I/O adapter performing efficient memory management |
| CN101176078A (en) * | 2005-03-17 | 2008-05-07 | 高通股份有限公司 | Method and system for optimizing translation lookaside buffer entries |
| US7802070B2 (en) * | 2006-06-13 | 2010-09-21 | Oracle America, Inc. | Approach for de-fragmenting physical memory by grouping kernel pages together based on large pages |
-
2010
- 2010-12-01 CN CN2010105684856A patent/CN102486751A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020044486A1 (en) * | 2000-10-16 | 2002-04-18 | Cheng-Sheng Chan | IC card with different page sizes to increase endurance |
| CN1682200A (en) * | 2002-09-13 | 2005-10-12 | 皇家飞利浦电子股份有限公司 | Translation lookaside buffer with partial tag hashed according to page size indicator |
| CN101176078A (en) * | 2005-03-17 | 2008-05-07 | 高通股份有限公司 | Method and system for optimizing translation lookaside buffer entries |
| US20060236063A1 (en) * | 2005-03-30 | 2006-10-19 | Neteffect, Inc. | RDMA enabled I/O adapter performing efficient memory management |
| US7802070B2 (en) * | 2006-06-13 | 2010-09-21 | Oracle America, Inc. | Approach for de-fragmenting physical memory by grouping kernel pages together based on large pages |
Non-Patent Citations (2)
| Title |
|---|
| 《计算机工程》 20100531 吴贞海 "基于快速上下文切换扩展的快速地址空间切换" 第36卷, 第10期 * |
| 吴贞海: ""基于快速上下文切换扩展的快速地址空间切换"", 《计算机工程》, vol. 36, no. 10, 31 May 2010 (2010-05-31) * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838608A (en) * | 2014-03-05 | 2014-06-04 | 深圳市中兴物联科技有限公司 | Method and device for page self-adaption of NAND Flash |
| CN103838608B (en) * | 2014-03-05 | 2019-05-24 | 深圳市中兴物联科技有限公司 | The method and device of NAND Flash page surface self-adaption |
| CN112162938A (en) * | 2015-08-10 | 2021-01-01 | 北京忆恒创源科技有限公司 | Large page memory allocation method and computer thereof |
| CN107392200A (en) * | 2017-08-23 | 2017-11-24 | 深圳市乐智教育科技有限公司 | It is a kind of to put the method read and talking pen |
| CN107392200B (en) * | 2017-08-23 | 2020-09-15 | 深圳市乐智教育科技有限公司 | Touch reading method and touch reading pen |
| WO2019127135A1 (en) * | 2017-12-27 | 2019-07-04 | 华为技术有限公司 | File page table management technique |
| US11237980B2 (en) | 2017-12-27 | 2022-02-01 | Huawei Technologies Co., Ltd. | File page table management technology |
| CN108717395A (en) * | 2018-05-18 | 2018-10-30 | 记忆科技(深圳)有限公司 | A kind of method and device reducing dynamic address mapping information committed memory |
| CN113296685A (en) * | 2020-05-29 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Data processing method and device and computer readable storage medium |
| CN113296685B (en) * | 2020-05-29 | 2023-12-26 | 阿里巴巴集团控股有限公司 | Data processing method and device and computer readable storage medium |
| CN112394884A (en) * | 2020-11-18 | 2021-02-23 | 珠海全志科技股份有限公司 | Method for reducing UBI subsystem management overhead, UBI subsystem and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101320594B (en) | Physical operation method of flash memory chip | |
| US20180089074A1 (en) | Techniques to Manage Key-Value Storage at a Memory or Storage Device | |
| CN102486751A (en) | Method for realizing virtual big page through small page NANDFLASH on micro memory system | |
| US20090106484A1 (en) | Data writing method for non-volatile memory and controller using the same | |
| US20130173874A1 (en) | System and Method for Pre-interleaving Sequential Data | |
| CN104102585A (en) | Mapping information recording method, memory controller and memory storage device | |
| CN101872644A (en) | Electronic storage device and storage method thereof | |
| CN103164343B (en) | Based on the paging of phase transition storage, ECC verification and multidigit forecasting method and structure thereof | |
| US8775722B2 (en) | Storing data in parallel in a flash storage device using on chip page shifting between planes | |
| CN111158579B (en) | Solid state hard disk and its data access method | |
| CN101464834A (en) | Flash memory data writing method and controller using same | |
| CN101661431B (en) | Block management method for flash memory, flash storage system and controller | |
| CN101788955A (en) | Flash memory data access method and its storage system and control system | |
| CN106802777A (en) | A kind of flash translation layer (FTL) control method for solid storage device | |
| CN109219797A (en) | For formatting the technology of non-volatile storage file | |
| KR20220091362A (en) | Utilizing nand buffer for dram-less multilevel cell programming | |
| CN101425338B (en) | Writing method of non-volatile memory and controller using this method | |
| CN101625661B (en) | Data management method, storage system and controller for flash memory | |
| CN101324899B (en) | Method for rapidly writing NAND type FLASH | |
| CN102800357A (en) | Program code loading and accessing method, memory controller and memory storage device | |
| US10872035B1 (en) | Systems and methods for managing an artificially limited logical space of non-volatile memory | |
| CN120660064A (en) | Method and apparatus for reducing memory capacity for storing page-related information in a NAND flash device | |
| US20090182932A1 (en) | Method for managing flash memory blocks and controller using the same | |
| CN102103546A (en) | Method and control unit for carrying out storage management on storage devices as well as related storage devices | |
| CN105630697A (en) | Storage structure for storing small file by MRAM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120606 |